Skip to main content
  1. Home
  2. Computing
  3. Business
  4. Gaming
  5. Mobile
  6. News

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

Leak suggests mobile version of Nvidia’s GTX 1070 and 1060 won’t differ much from the desktop

Add as a preferred source on Google

Now that Nvidia’s Pascal-based GeForce GTX 1070 and GTX 1060 cards are available on the market, the spotlight falls on the mobile versions of these graphics chips. While nothing official has hit the streets, reports have surfaced showing these two mobile GPUs listed separately in the GPU-Z application. So much for that rumor about scrapping high-end mobile versions for full-blown GPUs in notebooks? Perhaps not.

For starters, a screenshot provided by BenchLife shows that the mobile version of the GTX 1070 will have 2,048 CUDA cores, which is 128 more than the desktop version. There are also 64 Render Output Units, 170 Texture Memory Units, a pixel fill rate of 92.4 gigapixels per second, and a texture fill rate of 245.3 gigatexels per second. The chip is backed by 8GB of GDDR5 memory from Samsung, a 256-bit bus width, and a memory bandwidth of 256.3GB per second.

Recommended Videos

As for other details, the mobile GTX 1070 chip has a base clock speed of 1,443MHz, a boost clock speed of 1,645MHz, and a memory clock speed of 2,002MHz. Nvidia SLI is shown as disabled, and the chip shows it to be compatible with DirectCompute 5.0.

As for the mobile version of the GTX 1060, a screenshot of the GPU-Z app provided by PurePC shows that it has 1,280 CUDA cores, the same amount offered in the desktop version. Also, there are 48 Render Output Units, 106 Texture Memory Units, a pixel fill rate of 67.4 gigapixels per second, and a texture fill rate of 148.9 gigatexels per second.

The unannounced mobile chip will supposedly have 6GB of GDDR5 memory provided by Samsung, with a 192-bit bus width and a bandwidth of 192.2GB per second. The chip’s base clock speed shows to be 1,405MHz, its boost clock speed at 1,671MHz, and its memory clock speed at 2,002MHz. Nvidia SLI is also shown to be disabled for this specific graphics chip.

Basically, the mobile GTX 1060 offers similar specs as the desktop version, but with a lower clock speed. The desktop version, launched on Tuesday, has a base clock speed of 1,506MHz and a boost clock speed of 1,709MHz. As for the mobile GTX 1070 chip, the CUDA count is higher, as previously stated, but the clock speeds are lower, as the desktop version has a base clock of 1,506MHz, and a boost clock of 1,683MHz.

As the two GPU-Z screenshots suggest, Nvidia’s Pascal architecture seemingly allows the company to cram a desktop-grade GPU into a notebook, as the previous rumor suggested. Of the two examples, the GTX 1070 is the most altered component with the added cores and reduced clock speeds, but otherwise the difference isn’t that far off…. if the GPU-Z screenshots are indeed authentic.

In addition to the GPU-Z app, PurePC shows a screenshot of a 3DMark Firestrike benchmark using the mobile GTX 1060 chip. The gaming laptop used in the test also included an Intel Core i7-6700K processor and 16GB of system memory. This laptop obtained a score of 10,295 points in the benchmark, which seems mighty impressive for a notebook with a “mobile” GPU installed.

Kevin Parrish
Kevin started taking PCs apart in the 90s when Quake was on the way and his PC lacked the required components. Since then…
Qualcomm is set to ratchet up chip prices in September, and your next gadget upgrade could bear the brunt
The price hike could touch every Snapdragon-powered device category.
The new Qualcomm Snadragon 8 Elite Gen 5

I want you to sit with this for a second. Qualcomm, the company whose Snapdragon chips sit inside your Android phone and tablet, your Windows laptop, your Meta smart glasses, your Galaxy Watch, and your wireless earbuds, reportedly sent a letter to every major customer telling them prices are going up by double digits. 

The price hike will be in effect from September 1, 2026, a recent Bloomberg report claims. Essentially, all the companies placing their chip orders after that will pay a higher price. 

Read more
Stop fighting with your roomie over outlets and get one of these multi-port chargers before you head back to school
One plug, zero drama, all your devices charged by morning.
Satechi ChargeView

Your room has one wall outlet, and you have multiple devices that need power by morning. Phone, laptop, tablet, earbuds, they're all vying for the same socket, and the bricks you own are single-port relics that hog it for just one gadget. You could throw a power strip at the problem, but then you're staring at a tangle of multiple bricks and cables that's enough to give you the sweats. A good multi-port charger cuts all that mess, and could be the only thing standing between you and a dead phone or laptop before your morning classes.

Back-to-school season is a smart time to buy one. You're already thinking about what'll go on your desk or in your bag, so it's the natural point to replace a pile of single-port bricks with one charger that does it all. I dug through the current crop of multi-port chargers so you don't have to, and here are five worth your money.

Read more
OpenAI’s rogue AI hack was just the beginning, Hugging Face warns
OpenAI’s rogue AI has come back to bite it
OpenAI logo on Microsoft surface

Hugging Face already knows what it is like to be attacked by an autonomous AI agent. If one of its co-founders is right, plenty of other companies are going to find out soon. Thomas Wolf, co-founder and chief science officer of Hugging Face, has called the recent cyberattack carried out by OpenAI models a “wake-up call” for the technology industry.

Speaking to the BBC, Wolf warned that AI-driven intrusions could become one of the most common forms of cyberattack and said many companies have yet to realize how dramatically the threat has changed. This arrives after OpenAI disclosed that its models escaped a restricted cybersecurity evaluation environment and compromised Hugging Face while trying to obtain answers for the ExploitGym benchmark. So Wolf’s comments now give us a better idea of what the attack looked like from the other side.

Read more